Mercurial > repos > iuc > roary

comparison roary.xml @ 10:9b2b122d0415 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/roary commit 2652aac9012d0a19c17e06536bb0e300d048bbf5
author iuc
date Sun, 11 Aug 2024 20:29:52 +0000
parents 91887494eb97
children
comparison
equal deleted inserted replaced
9:91887494eb97 10:9b2b122d0415
1 <tool id="roary" name="Roary" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"> 1 <tool id="roary" name="Roary" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
2 <description>the pangenome pipeline - Quickly generate a core gene alignment from gff3 files</description> 2 <description>the pangenome pipeline - Quickly generate a core gene alignment from gff3 files</description>
3 <macros> 3 <macros>
4 <token name="@TOOL_VERSION@">3.13.0</token> 4 <token name="@TOOL_VERSION@">3.13.0</token>
5 <token name="@VERSION_SUFFIX@">2</token> 5 <token name="@VERSION_SUFFIX@">3</token>
6 </macros> 6 </macros>
7 <xrefs> 7 <xrefs>
8 <xref type="bio.tools">roary</xref> 8 <xref type="bio.tools">roary</xref>
9 </xrefs> 9 </xrefs>
10 <requirements> 10 <requirements>
11 <requirement type="package" version="@TOOL_VERSION@">roary</requirement> 11 <requirement type="package" version="@TOOL_VERSION@">roary</requirement>
12 </requirements> 12 </requirements>
13
14 <command detect_errors="exit_code"><![CDATA[ 13 <command detect_errors="exit_code"><![CDATA[
15 #import re 14 #import re
16 #set $filenames = list() 15 #set $filenames = list()
17 ## Roary resolves symbolic links and breaks if there is whitespace in the path. 16 ## Roary resolves symbolic links and breaks if there is whitespace in the path.
18 ## Copying and renaming the files resolves that issue. 17 ## Copying and renaming the files resolves that issue.
21 cp '$gff' $filename && 20 cp '$gff' $filename &&
22 $filenames.append(str($filename)) 21 $filenames.append(str($filename))
23 #end for 22 #end for
24 23
25 roary 24 roary
26 -f out 25 -f out
27 -p \${GALAXY_SLOTS:-1} 26 -p \${GALAXY_SLOTS:-1}
28 -e 27 -e
29 -n 28 -z
30 -i '$percent_ident' 29 -n
31 -cd '$core_diff' 30 -i '$percent_ident'
32 -g '$advanced.maxclust' 31 -cd '$core_diff'
33 $advanced.split_para 32 -g '$advanced.maxclust'
34 -t '$advanced.trans_tab' 33 $advanced.split_para
35 -iv '$advanced.mcl' 34 -t '$advanced.trans_tab'
35 -iv '$advanced.mcl'
36 36
37 #for $f in $filenames 37 #for $f in $filenames
38 '$f' 38 '$f'
39 #end for 39 #end for
40 40
41 ]]> </command> 41 ]]></command>
42
43 <inputs> 42 <inputs>
44 <conditional name="gff_input"> 43 <conditional name="gff_input">
45 <param name="gff_input_selector" type="select" label="Individual gff files or a dataset collection" help="Select between individual gff files or a collection of gff files"> 44 <param name="gff_input_selector" type="select" label="Individual gff files or a dataset collection" help="Select between individual gff files or a collection of gff files">
46 <option value="individual">Individual</option> 45 <option value="individual">Individual</option>
47 <option value="collection">Collection</option> 46 <option value="collection">Collection</option>
48 </param> 47 </param>
49 <when value="individual"> 48 <when value="individual">
50 <param name="gffs" type="data" multiple="true" min="2" format="gff,gff3" label="select gff inputs to Roary" help="Select the files you wish to send to Roary, must be in gff3 format with the sequence data at the end of the file." /> 49 <param name="gffs" type="data" format="gff,gff3" min="2" label="select gff inputs to Roary" help="Select the files you wish to send to Roary, must be in gff3 format with the sequence data at the end of the file." multiple="true"/>
51 </when> 50 </when>
52 <when value='collection'> 51 <when value="collection">
53 <param name="gffs" type="data_collection" collection_type="list" format="gff,gff3" label="Dataset collection to submit to Roary" help="A dataset list collection of gff3 files to send to Roary for analysis." /> 52 <param name="gffs" type="data_collection" format="gff,gff3" label="Dataset collection to submit to Roary" help="A dataset list collection of gff3 files to send to Roary for analysis." collection_type="list"/>
54 </when> 53 </when>
55 </conditional> 54 </conditional>
56 <param name="percent_ident" type="integer" value="95" label="minimum percentage identity for blastp" help="Sets the minimum percentage identity for protein matches" /> 55 <param name="percent_ident" type="integer" value="95" label="minimum percentage identity for blastp" help="Sets the minimum percentage identity for protein matches"/>
57 <param name="core_diff" type="float" value="99.0" label="percentage of isolates a gene must be in to be core" help="The total percentage of the isolates that must have the gene for it to be considered a core gene." /> 56 <param name="core_diff" type="float" value="99.0" label="percentage of isolates a gene must be in to be core" help="The total percentage of the isolates that must have the gene for it to be considered a core gene."/>
58 57 <param name="outputs" type="select" label="Additional outputs" help="Summary statistics, core gene alignments and Gene Presence/Absence tables are always produced." multiple="true" display="checkboxes">
59 <param name="outputs" type="select" multiple="true" display="checkboxes" label="Additional outputs" help="Summary statistics, core gene alignments and Gene Presence/Absence tables are always produced.">
60 <option value="abg_nw">Accessory binary genes in newick format</option> 58 <option value="abg_nw">Accessory binary genes in newick format</option>
61 <option value="abg_fa">Accessory binary genes in fasta format</option> 59 <option value="abg_fa">Accessory binary genes in fasta format</option>
62 <option value="accgraph">Accessory graph in dot format</option> 60 <option value="accgraph">Accessory graph in dot format</option>
63 <option value="acchead_embl">Accessory header file in embl format</option> 61 <option value="acchead_embl">Accessory header file in embl format</option>
64 <option value="acctab">Accessory gene table in tabular format</option> 62 <option value="acctab">Accessory gene table in tabular format</option>
72 <option value="numpangene_rtab">Number of Genes in Pan Genome in Rtab format</option> 70 <option value="numpangene_rtab">Number of Genes in Pan Genome in Rtab format</option>
73 <option value="numnew_rtab">Number of New Genes in Rtab format</option> 71 <option value="numnew_rtab">Number of New Genes in Rtab format</option>
74 <option value="numuniq_rtab">Number of Unique Genes in Rtab format</option> 72 <option value="numuniq_rtab">Number of Unique Genes in Rtab format</option>
75 <option value="pangenomeref">FASTA file which contains a single representative nucleotide sequence from each of the clusters in the pan genome (core and accessory)</option> 73 <option value="pangenomeref">FASTA file which contains a single representative nucleotide sequence from each of the clusters in the pan genome (core and accessory)</option>
76 </param> 74 </param>
77
78 <section name="advanced" title="Advanced options" expanded="false"> 75 <section name="advanced" title="Advanced options" expanded="false">
79 <param name="maxclust" type="integer" value="50000" label="Maximum number of clusters" help="The maximum number of clusters to assign proteins" /> 76 <param name="maxclust" type="integer" value="50000" label="Maximum number of clusters" help="The maximum number of clusters to assign proteins"/>
80 <param name="split_para" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Don't split paralogs" help="Click yes so that paralogs aren't split." /> 77 <param name="split_para" type="boolean" truevalue="-s" falsevalue="" checked="False" label="Don't split paralogs" help="Click yes so that paralogs aren't split."/>
81 <param name="trans_tab" type="integer" value="11" label="Translation table to use [1 or 4 or 11]" help="DNA -> RNA translation table to use. Roary is designed for prokaryotes and so tables 1, 4 or 11 will work, others could be problematic." /> 78 <param name="trans_tab" type="integer" value="11" label="Translation table to use [1 or 4 or 11]" help="DNA -&gt; RNA translation table to use. Roary is designed for prokaryotes and so tables 1, 4 or 11 will work, others could be problematic."/>
82 <param name="mcl" type="float" value="1.5" label="MCL inflation value" help="This is an advanced setting, change only if you know what you are doing and then at your own risk!" /> 79 <param name="mcl" type="float" value="1.5" label="MCL inflation value" help="This is an advanced setting, change only if you know what you are doing and then at your own risk!"/>
83 </section> 80 </section>
84
85 </inputs> 81 </inputs>
86
87 <outputs> 82 <outputs>
88 <data format="tabular" name="sumstats" label="${tool.name} on ${on_string} Summary statistics" from_work_dir="out/summary_statistics.txt" /> 83 <data format="tabular" name="sumstats" label="${tool.name} on ${on_string} Summary statistics" from_work_dir="out/summary_statistics.txt"/>
89 <data format="fasta" name="core_gene_aln" label="${tool.name} on ${on_string} Core Gene Alignment" from_work_dir="out/core_gene_alignment.aln" /> 84 <data format="fasta" name="core_gene_aln" label="${tool.name} on ${on_string} Core Gene Alignment" from_work_dir="out/core_gene_alignment.aln"/>
90 <data format="csv" name="gene_p_a" label="${tool.name} on ${on_string} Gene Presence Absence" from_work_dir="out/gene_presence_absence.csv" /> 85 <data format="csv" name="gene_p_a" label="${tool.name} on ${on_string} Gene Presence Absence" from_work_dir="out/gene_presence_absence.csv"/>
91 <data format="fasta" name="acc_bin" label="${tool.name} on ${on_string} Accessory Binary Genes" from_work_dir="out/accessory_binary_genes.fa"> 86 <data format="fasta" name="acc_bin" label="${tool.name} on ${on_string} Accessory Binary Genes" from_work_dir="out/accessory_binary_genes.fa">
92 <filter>outputs and 'abg_fa' in outputs</filter> 87 <filter>outputs and 'abg_fa' in outputs</filter>
93 </data> 88 </data>
94 <data format="nhx" name="acc_bin_new" label="${tool.name} on ${on_string} Accessory Binary Genes (Newick)" from_work_dir="out/accessory_binary_genes.fa.newick"> 89 <data format="nhx" name="acc_bin_new" label="${tool.name} on ${on_string} Accessory Binary Genes (Newick)" from_work_dir="out/accessory_binary_genes.fa.newick">
95 <filter>outputs and 'abg_nw' in outputs</filter> 90 <filter>outputs and 'abg_nw' in outputs</filter>
135 </data> 130 </data>
136 <data format="fasta" name="pan_genome_ref" label="${tool.name} on ${on_string} pan-genome reference" from_work_dir="out/pan_genome_reference.fa"> 131 <data format="fasta" name="pan_genome_ref" label="${tool.name} on ${on_string} pan-genome reference" from_work_dir="out/pan_genome_reference.fa">
137 <filter>outputs and 'pangenomeref' in outputs</filter> 132 <filter>outputs and 'pangenomeref' in outputs</filter>
138 </data> 133 </data>
139 </outputs> 134 </outputs>
140
141 <tests> 135 <tests>
142 <test> 136 <test expect_num_outputs="3">
143 <param name="gff_input_selector" value="individual" /> 137 <param name="gff_input_selector" value="individual"/>
144 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3" /> 138 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3"/>
145 <output name="sumstats" file="out/summary_statistics.txt" ftype="tabular" /> 139 <output name="sumstats" file="out/summary_statistics.txt" ftype="tabular"/>
146 </test> 140 </test>
147 <test> 141 <test expect_num_outputs="3">
148 <param name="gff_input_selector" value="individual" /> 142 <param name="gff_input_selector" value="individual"/>
149 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3" /> 143 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3"/>
150 <param name="percent_ident" value="50" /> 144 <param name="percent_ident" value="50"/>
151 <param name="core_diff" value="50.0" /> 145 <param name="core_diff" value="50.0"/>
152 <output name="sumstats" file="test2/summary_statistics.txt" ftype="tabular" /> 146 <output name="sumstats" file="test2/summary_statistics.txt" ftype="tabular"/>
153 </test> 147 </test>
154 </tests> 148 </tests>
155
156 <help><![CDATA[ 149 <help><![CDATA[
157 **Roary** 150 **Roary**
158 151
159 Roary is a high speed stand alone pan genome pipeline, which takes annotated assemblies in GFF3 format (produced by Prokka) and calculates the pan genome. Using a standard desktop PC, it can analyse datasets with thousands of samples, something which is computationally infeasible with existing methods, without compromising the quality of the results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a single processor. To perform this analysis using existing methods would take weeks and hundreds of GB of RAM. 152 Roary is a high speed stand alone pan genome pipeline, which takes annotated assemblies in GFF3 format (produced by Prokka) and calculates the pan genome. Using a standard desktop PC, it can analyse datasets with thousands of samples, something which is computationally infeasible with existing methods, without compromising the quality of the results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a single processor. To perform this analysis using existing methods would take weeks and hundreds of GB of RAM.
160 153
184 177
185 178
186 For further info see: http://sanger-pathogens.github.io/Roary/ 179 For further info see: http://sanger-pathogens.github.io/Roary/
187 180
188 ]]> </help> 181 ]]> </help>
189
190 <citations> 182 <citations>
191 <citation type="doi">10.1093/bioinformatics/btv421</citation> 183 <citation type="doi">10.1093/bioinformatics/btv421</citation>
192 </citations> 184 </citations>
193
194 </tool> 185 </tool>